This application includes subject matter similar to the subject matter described in the following co-owned applications: U.S. application Ser. No. 14/484,119, filed Sep. 11, 2014, entitled “Methods System and Articles of Manufacture for Using a Predictive Model to Determine Tax Topics Which are Relevant to a Taxpayer in Preparing an Electronic Tax Return”; U.S. application Ser. No. 14/530,305, filed Oct. 31, 2014, now U.S. Pat. No. 10,013,721, issued Jul. 3, 2018, entitled “Identification of Electronic Tax Return Errors Based on Declarative Constraints”; U.S. application Ser. No. 14/530,369, filed Oct. 31, 2014, entitled “Predictive Model Based Identification of Potential Errors in Electronic Tax Return”; U.S. application Ser. No. 14/674,582, filed Mar. 31, 2015, entitled “Methods, Systems and Computer Program Products for Calculating an Estimated Result of a Tax Return”; U.S. application Ser. No. 14/607,935, filed Jan. 28, 2015, entitled “Methods and Systems for Identifying Product Defects Within a Tax Return Preparation System”; and U.S. application Ser. No. 14/698,645, filed Apr. 28, 2015, entitled “Systems for Identifying Abandonment Indicators for an Electronic Tax Return Preparation Program.” The contents of which are fully incorporated herein by reference.
Embodiments are directed to computer analytic systems for allocating resources of an electronic tax return preparation program.
In one embodiment directed to a computer analytic system for allocating resources of an electronic tax return preparation system, the system includes an information module configured to collect taxpayer data of a user, where the taxpayer data includes an indicator of an increased likelihood that the user will abandon the electronic tax return preparation program (“abandonment indicator”). The system also includes a memory module configured to store the collected taxpayer data. The system further includes a retention module configured to analyze the collected taxpayer data and generate a resource allocation recommendation based on the collected taxpayer data.
In a single or multiple embodiments, the taxpayer data also includes data selected from the group consisting of taxpayer information entered by the user, taxpayer information relating to the taxpayer obtained from one or more third parties, actions taken by the user in the electronic tax return preparation program, and whether the user has completed an electronic tax return using the electronic tax return preparation program or abandoned the electronic tax return preparation program.
In a single or multiple embodiments, the retention module includes a workflow location tracker. In those embodiments, analyzing the collected taxpayer data includes the workflow location tracker identifying the last location in a workflow of the electronic tax return preparation program occupied by the user before the user abandoned the electronic tax return preparation program. In those embodiments, the resource allocation recommendation includes offering to the user an additional resource related to the identified last location occupied by the user.
In a single or multiple embodiments, the retention module includes a workflow activity history tracker. In those embodiments, analyzing the collected taxpayer data includes the workflow activity history tracker identifying a workflow activity history of the user before the user abandoned the electronic tax return preparation program. In those embodiments, the resource allocation recommendation includes offering the user an additional resource related to the workflow activity history of the user.
In a single or multiple embodiments, the retention module includes a taxpayer characteristic identifier. In those embodiments, analyzing the collected taxpayer data includes the taxpayer characteristic identifier determining a correlation between a taxpayer characteristic and the indicator. In those embodiments, the resource allocation recommendation includes offering the user an additional resource related to the taxpayer characteristic. Determining a correlation may include the taxpayer characteristic identifier analyzing the indicator. Analyzing the collected taxpayer data may also include the taxpayer characteristic identifier determining a correlation between a plurality of taxpayer characteristics and the indicator. In those embodiments, the resource allocation recommendation includes offering the user one or more additional resources related to the plurality of taxpayer characteristics.
In a single or multiple embodiments, the retention module includes a retention sub-module. In those embodiments, analyzing the collected taxpayer data includes the retention sub-module identifying a user characteristic shared by users who completed an electronic tax return using the electronic tax return preparation program or abandoned the electronic tax return preparation program. In those embodiments, the resource allocation recommendation includes offering the user an additional resource related to the user characteristic.
In a single or multiple embodiments, the retention module includes a plurality of retention sub-modules. In those embodiments, analyzing the collected taxpayer data includes the plurality of retention sub-modules identifying a plurality of user characteristics shared by users who completed an electronic tax return using the electronic tax return preparation program or abandoned the electronic tax return preparation program. In those embodiments, the resource allocation recommendation includes offering the user an additional resource related to the user characteristics. The retention sub-module and/or the plurality of retention sub-modules may be selected from the group consisting of a clustering module, a k-means clustering module, a support vector machine, a decision tree module, a Naïve Bayesian classifier, and a neural network.
In a single or multiple embodiments, the additional resource is a computer, human or financial resource.
In a single or multiple embodiments, the computer analytic system is configured to be activated after a predetermined number of taxpayers perform an action in the electronic tax return preparation program. Alternatively or additionally, the computer analytic system may be configured to be iteratively activated each time predetermined numbers of taxpayers perform an action in the electronic tax return preparation program. In those embodiments, a predetermined number for a first iteration may be different from a predetermined number for a second iteration. The action may be selected from the group consisting of activate the electronic tax return preparation program, perform an action in the electronic tax return preparation program, and abandon the electronic tax return preparation program.
In a single or multiple embodiments, the computer analytic system is configured to be activated each time a taxpayer abandons the electronic tax return preparation program. Alternatively or additionally, the computer analytic system may be configured to be activated after a predetermined time. Further, alternatively or additionally, the computer analytic system may be configured to be manually activated.
In a single or multiple embodiments, the indicator is a numerical indicator. Alternatively or additionally, the memory module may include a plurality of files, a table, or a database configured to store taxpayer information relating to a plurality of taxpayers, where the files, table and database are sortable by respective indicators.
The foregoing and other aspects of embodiments are described in further detail with reference to the accompanying drawings, in which the same elements in different figures are referred to by common reference numerals, wherein:
In order to better appreciate how to obtain the above-recited and other advantages and objects of various embodiments, a more detailed description of embodiments is provided with reference to the accompanying drawings. It should be noted that the drawings are not drawn to scale and that elements of similar structures or functions are represented by like reference numerals throughout. It will be understood that these drawings depict only certain illustrated embodiments and are not therefore to be considered limiting of scope of embodiments.
Like most consumer software, current electronic tax preparation programs present the same general user experience for all users. This results is an inefficient use of resources (e.g., computing, human and/or financial resources), because these programs do not take into account a particular user's particular characteristics and tailor at least portions of the user experience to user characteristics. Examples of user characteristics include, but are not limited to, likelihood of abandoning the electronic tax return preparation program, likelihood of completing an electronic tax return using the program, and likelihood of returning as a program user in the next tax year. The computer analytic systems described in this application are directed to providing more efficient use of electronic tax return preparation program resources by allocating system resources according to user characteristics.
For example, each tax year, millions of taxpayers start preparing their taxes using an electronic tax return preparation program only to abandon the tax-preparation process before completion. These cases of abandonment result in lost time for the taxpayers and lost users for the electronic tax return preparation program. The first step in addressing the abandonment problem is identifying characteristics/reasons/indicators that the users abandon the electronic tax return preparation program. The first step is addressed by U.S. application Ser. No. 14/698,645, filed Apr. 28, 2015, the contents of which have been previously incorporated by reference. The second step is to address those characteristics/reasons/indicators using the electronic tax return preparation program. The computer analytic systems described in this application are directed to the second step in addressing the abandonment problem by intelligent resource utilization tailored to user characteristics to reduce the likelihood that a particular user will abandon the application.
Embodiments described in this application are directed to computer analytic systems for allocating resources of an electronic tax return preparation program based on the characteristics of users thereof. In particular, the systems collect taxpayer data relating to a user of the electronic tax return preparation program, including one or more indicators of an increased likelihood that the user will abandon an electronic tax return preparation program (“abandonment indicator”). The computer analytic systems then analyze the collected taxpayer data and generate a resource allocation recommendation based on the collected taxpayer data.
The embodiments described herein address the program abandonment problem by providing differential treatment to users with an increased likelihood of abandonment. The differential treatment is tailored to the particular reason, indicator or user characteristic associated with an increased likelihood of abandonment to better address the reasons for abandonment.
In the described embodiments, many systems can be used to allocate resources of an electronic tax return preparation program based on user characteristics. For instance, in one embodiment, the abandonment indicator is that the user quit the program at the page most commonly associated with abandonment. Based on the indicator (and perhaps other taxpayer data), the computer analytic system may generate a resource allocation recommendation that the user be sent a message (e.g., email or SMS) offering additional assistance relating to the page, up to and including, help from a live user support associate. The indicator or other taxpayer information may have been provided by a retention module of the computer analytic system, other modules (e.g., an abandonment module) in the computer analytic system, an interview with the user upon quitting, or various other sources.
In one specific embodiment, the retention module of the computer analytic system includes a workflow location tracker, which determines the user's location in the workflow immediately prior to the user quitting (or abandoning) the program (i.e., “user's last location”). After the system collects taxpayer data including an abandonment indicator that the user has quit the program at the page most commonly associated with abandonment, the system analyzes the collected taxpayer data and the user's last location and generates a resource allocation recommendation as described above. Accordingly, the system may recommend that a user who quits the program at a problematic workflow location receive increased system resources related to the problematic workflow location, i.e. the user's last location.
As used in this application, a “user” or “taxpayer” includes, but is not limited to, a person preparing a tax return using tax return preparation software. The “user” or “taxpayer” may or may not be obligated to file the tax return. As used in this application, a “previous tax return” or “prior tax return” includes, but is not limited to, a tax return (in electronic or hard copy form) for a year before the current tax year. As used in this application, “tax data” includes, but is not limited to, information that may affect a user's income tax burden, including information typically included in a tax return. As used in this application, “taxpayer data” includes, but is not limited to, information relating to a taxpayer, including, but not limited to, tax data. The terms “tax data” and “taxpayer data,” as used in this application, also include, but are not limited to, partially or fully completed tax forms (electronic and hard copy) that include information typically included in a tax return. As used in this application, “abandoning an electronic tax return preparation program” includes, but is not limited to: (1) deleting a taxpayer file/account on the program; (2) quitting the program without returning to the user file for a predetermined amount of time (e.g., 30 days) or before a tax filing deadline (e.g., April 15); or (3) quitting the program and filing taxes without using the program.
As used in this application, “computer,” “computer device” and “computing device” include, but are not limited to, a computer (laptop or desktop) and a computer or computing device of a mobile communication device, smartphone and tablet computing device such as an IPAD (available from Apple Inc. of Cupertino, Calif.). As used in this application, “tax return preparation system,” “tax return preparation computing device,” “tax return preparation computer,” “tax return preparation software,” “tax return preparation module,” “tax return preparation application,” or “tax return preparation program” include, but are not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can prepare tax returns.
As used in this application, “information module” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can collection taxpayer data for analysis. As used in this application, “memory module” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can store taxpayer data in proper formats for analysis. As used in this application, “abandonment module” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can analyze taxpayer data and generate an abandonment indicator. As used in this application, “retention module” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can analyze taxpayer data and generate a resource allocation recommendation.
As used in this application, “tax logic agent” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can analyze tax data according to one or more sets of rules. As used in this application, “predictive model” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can generate resource allocation recommendations according to one or more algorithms. As used in this application, “tax calculation engine” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can perform tax calculations including, not limited to, calculating the results of electronic tax returns. As used in this application, “user interface controller” includes, but is not limited to, one or more separate and independent components of a computer that must be added to a general purpose computer before the computer can control a user interface.
Referring to
The tax preparation system 300 also includes or involves a special purpose intermediate computer 320 managed by a host 325. Intermediate computer 320 is specially or particularly configured or operable to host an on-line version of tax return preparation program 312 and to store taxpayer data 314. The intermediate computer 320 can also format and electronically file electronic tax returns with a computer 330 of a tax authority 335. Examples of a tax authority or other tax collecting entity include a federal tax authority, e.g., the Internal Revenue Service (IRS), a state tax authority or other tax collecting entity of the United States, a state thereof, or another country or state thereof (generally, “tax authority”). Examples of hosts 325 that provide the special purpose intermediate computer 320 include, for example, Intuit Inc., which provides a second or intermediate computer 320 or server of the Intuit Electronic Filing Center for electronically filing tax returns 312 and other hosts 325 that provide tax preparation programs 312 and electronic filing servers.
According to embodiments, intermediate computer 320 further comprises or accesses a computer analytic system, program or module 316 (“computer analytic system” in
In the illustrated embodiment, tax return preparation program 312 is a local program that executes on preparer computer 310, but embodiments may also involve on-line tax preparation programs 312 hosted by intermediate computer 320 and accessed by preparer computer 310. For ease of explanation, reference is made generally to tax return preparation program 312.
For these and other communication purposes, preparer computer 310 is operably coupled to or in communication with second or intermediate computer 320 through a network 350a, and intermediate computer 320 is operably coupled to or in communication with tax authority computer 330 through a network 350b. Each of the networks 350a-b and other networks discussed herein (generally, network 350) may be different, or two or more networks 350 may be the same depending on the system configuration and communication protocols employed. One or more or all of networks 350 may be, for example, a wireless or cellular network, a Local Area Network (LAN) and/or a Wide Area Network (WAN). Reference to network 350 generally is not intended to refer to a specific network or communications protocol, and embodiments can be implemented using various networks 350 and combinations thereof.
The information module 910 typically collects taxpayer data from an electronic tax return preparation program. In one embodiment, the information module 910 is operatively coupled to the input/output module 940, and directs the input/output module 940 to collect the taxpayer data (e.g., from an electronic tax return preparation program). For these purposes, the information module 910 is configured to communicate with the electronic tax return preparation program to instruct the program regarding the types of information to retain. The taxpayer data can include, but is not limited to: (1) taxpayer information entered by the respective taxpayers (including data from prior years' tax returns); (2) taxpayer information relating to respective taxpayers obtained from third parties (e.g., data sources 48 from
The information module 910 is also configured to collect taxpayer information including an abandonment indicator. The taxpayer information also includes identifying information (e.g., social security number or name) to enable the computer analytic system 902 to issue resource allocation recommendations relating to the particular user. However, the other taxpayer information can be stored (e.g., for further system analysis) without the identifying information. This limitation would facilitate collection of taxpayer information from a larger cohort of taxpayers, due to privacy concerns. In a simple embodiment, the taxpayer information includes only an abandonment indicator and identifying information.
The memory module 920 is configured to store the collected taxpayer data. The memory module 920 may include a plurality of files, a table and/or a database configured to store taxpayer information relating to respective ones of the taxpayers. The files, table and/or database may be sortable by respective abandonment indicators.
The retention module 960 this configured to analyze the collected taxpayer data, including the abandonment indicator, using a variety of analysis tools and predictive models, as instantiated in retention sub-modules 970. The result of the analysis is to generate a resource allocation recommendation for the electronic tax return preparation program. In one embodiment, the retention module 960 sends the resource allocation recommendation to the electronic tax return preparation program, via the input/output module 940. In some embodiments, the tax return preparation program uses the resource allocation recommendation to direct reallocation of resources (e.g., computer, human and/or financial resources) to a particular user at increased risk of abandonment.
One example of a retention sub-module 970 is a workflow location tracker 950 that is configured to track a user's last workflow location immediately prior to the user quitting or abandoning the program, as described above. The retention module 960 analyzes the last workflow location of a user together with an abandonment indicator stating that the user has quit the program at the workflow location most commonly associated with abandonment. In one embodiment, if the most common abandonment location (e.g., 250,000 out of 5,000,000 users who abandoned the program) and last workflow location is a page for entering mortgage interest deduction, the retention module 960 may generate a resource allocation recommendation that the user (who quit the program at that page) receive additional resources relating to the mortgage interest deduction page in the workflow.
In one embodiment, the additional resource is a computer resource such as assignment to faster or less loaded servers, faster networks, servers with increased memory or additional processors. In another embodiment, the additional resource is a human resource such as access to a customer service representative, including a representative with specialized training related to the abandonment indicator (e.g., special guidance on how to proceed through the mortgage interest deduction page). In still another one, the additional resource is a financial resource such as a discount on the current tax filing or a coupon for a future discount.
Another example of a retention sub-module 970 is a workflow activity history tracker 950 that is configured to identify a user's workflow activity history. The workflow activity history can be a predetermined number of pages (e.g., 10 pages) accessed by a user before quitting or abandoning the electronic tax return preparation program. The retention module 960 analyzes the workflow activity history of a user together with an abandonment indicator stating that the user is becoming frustrated with the program and may abandon the program to call a human tax preparer. This abandonment indicator may be generated from an analysis of the workflow activity history of the user (e.g., a series of questions relating to a particular tax topic). The analysis is similar to the analysis described above with respect to the last workflow location. In response, the analysis, the retention module 960 may generate a resource allocation recommendation that the user (with the above-described workflow activity history) receive additional resources (computer, human and/or financial) relating to the particular tax topic.
Still another example of a retention sub-module 970 is a taxpayer characteristic identifier 970 that is configured to determining a correlation between a taxpayer characteristic and an abandonment indicator. In one embodiment, the taxpayer characteristic identifier 970 can determine that the user is price-sensitive, and the abandonment indicator states that price-sensitive users are more likely to abandon the program. In response, the retention module 960 can generate a resource allocation recommendation that the user receive additional financial resources (e.g., a filing fee discount).
In another embodiment, the taxpayer characteristic identifier 970 can determine that the user will have a reduction in deductions and/or credits compared to last year, and the abandonment indicator states that users with reductions in deductions and/or credits are more likely to abandon the program. In response, the retention module 960 can generate a resource allocation recommendation that the user receive additional human resources (e.g., access to a customer service representative with specialized training to identify deductions and credits).
In still another embodiment, the taxpayer characteristic identifier 970 can determine that the user is becoming frustrated with the response time of the program, and the abandonment indicator states that users with response time frustrations are more likely to abandon the program. In response, the retention module 960 can generate a resource allocation recommendation that the user receive additional computer resources (e.g., assignment to faster or less loaded servers, or faster networks).
In yet another embodiment, the taxpayer characteristic identifier 970 can determine that the user is a loyal customer for many years with an increasingly complicated tax situation. Further, the abandonment indicator states that users with increasingly complicated tax situations are more likely to abandon the program for a human accountant. In response, the retention module 960 can generate a resource allocation recommendation that the user receive additional computer resources (e.g., assignment to faster or less loaded servers, or faster networks for faster processing of complicated tax return), additional human resources (e.g., specialized advice on their specific tax situation and/or a human tax expert return review), and/or additional financial resources (special loyalty discounts).
In still another embodiment, the taxpayer characteristic identifier 970 can determine that the user files many returns using the program each tax year. Further, the abandonment indicator states that user is more likely to abandon the program. In response, the retention module 960 can generate a resource allocation recommendation that the user receive additional resources (e.g., computer, human or financial). In some embodiments, the amount of additional resources recommended for such a user may be greater than the amount of additional resources recommended for a user who files a single return each tax year.
Other examples of retention sub-modules 970 are predictive engines 970, including, but not limited to, clustering modules (e.g., k-means clustering modules), support vector machines, decision tree modules, Naïve Bayesian classifiers, and neural networks. Individual ones or groups of these predictive engines 970 can be used to identify taxpayer characteristics correlated/associated with abandonment indicators.
While retention modules 960 and sub-modules 970 have been described as configured to identify taxpayer characteristics correlated/associated with abandonment indicators, retention modules 960 and sub-modules 970 may also be configured to identify taxpayer characteristics correlated/associated with completing electronic tax returns using a specific electronic tax return preparation program. In those embodiments, the retention modules 960 generate resource allocation recommendations designed to encourage a user to adopt such “positive” characteristics.
The computer analytic system 900 depicted in
The computer analytic system 900 can be configured to self-activate iteratively each time a predetermined number of taxpayers perform one or more actions to repeatedly analyze the growing set of taxpayer data using more accurate (i.e., closer to “the truth”) and precise (i.e., more repeatable) abandonment indicators, which in turn facilitate more appropriate responsive actions to reduce abandonment of the program.
In one embodiment, the computer analytic system 900 can be configured to self-activate each time a taxpayer quits and/or abandons the electronic tax return preparation program. In an alternative embodiment, the computer analytic system 900 can be activated by a user (e.g., a system analyst).
As generally illustrated in
More specifically, during runtime, TLA 410 reads runtime 442 from data store 440, and a UI management module or controller 430 and a tax calculation engine 480 are also in communication with the data store 440. TLA 410 is operable to receive runtime or instance data 442 (generally, runtime data 442) that is based on a “dictionary” of terms of a data model or schema 446 (generally, schema 446). Schema 446 may specify, define or list tax-related concepts or terms, e.g., by names, type or category and hierarchy such as “name,” “social security number,” “citizenship,” “address,” “employer,” “interest,” “dividends,” “mortgage,” “deduction,” “tax credit,” “capital gain,” etc. An instance 442 is instantiated or created for the collection of data received and for each term or topic of schema 446. Schema 446 may also specify data constraints such as a certain format of questions and answers (e.g., answer is binary (Y/N) or a number/value). It will be understood that the schema 446 may define hundreds or thousands of such concepts or terms and may be defined in various ways, one example is based on an Extensible Markup Language (XML) schema. Non-limiting examples of schemas 446 that may be utilized in embodiments include Modernized E-File (MeF) and MeF++ schemas. Further, it will be understood that embodiments may utilize various other schemas, and that these schemas are provided as a non-limiting example of schema 446 that can be utilized in embodiments.
With continuing reference to
Examples of tax data include data obtained from W-2 forms, data obtained from 1099-INT forms, data obtained from other investment income (INV), filing status, and number of dependents. Tax data can be derived from user inputs. That is to say the user (e.g., a taxpayer) will enter this information from a user interface as described herein. In other embodiments, however, tax data may be obtained from information that is automatically obtained by the tax preparation software. For example, in some embodiments, tax documents may be imaged or scanned with relevant data being automatically extracted using Object Character Recognition (OCR) techniques. In other embodiments, prior tax returns may be used by the tax preparation software to extract information (e.g., name, potential dependents, address, and social security number). Online resources such as financial services websites or other user-specific websites can be crawled and scanned to scrape or otherwise download tax data. Additional third party information sources such as credit bureaus, government databases, and the like can also be used by the tax preparation software to obtain tax data.
In still other embodiments, tax data may be derived or otherwise calculated. For example, while the number of dependents may be manually entered by a taxpayer, those dependent may not all be “qualifying” dependents for tax purposes. In such instances, the actual number of “qualified” dependents may be derived or calculated by the tax preparation software.
TLA 410 may also receive or otherwise incorporate information from statistical/life knowledge module 490. Statistical/life knowledge module 490 contains statistical or probabilistic data related to the current or other users of the tax return preparation application and/or other taxpayers. For example, statistical/life knowledge module 490 may indicate that taxpayers residing within a particular zip code are more likely to be homeowners than renters.
Data that is contained within statistic/life knowledge module 490 may be obtained by analyzing aggregate tax data of a large body of taxpayers. For example, entities having access to tax filings may be able to mine their own proprietary data to establish connections and links between various taxpayer characteristics and tax topics. This information may be contained in a database or other repository that is accessed by statistic/life knowledge module 490. This information may be periodically refreshed or updated to reflect the most up-to-date relationships. Generally, the data contained in statistic/life knowledge module 490 is not specific to a particular taxpayer but is rather generalized to characteristics shared across a number of taxpayers although in other embodiments, the data may be more specific to an individual taxpayer.
The system 400 also includes a UI controller 430. TLA 410 provides to UI controller 430 a non-binding suggestion 411 comprising a selected question or topic 461 to be addressed. In the illustrated embodiment, UI controller 430 includes a UI or user experience manager 431 that determines how to process non-binding suggestions 411 with selected questions or topics 461 and generates an interview screen 432 for the UI or selects an interview screen 432 of the UI based on the question or topic 461 of non-binding suggestion 411. UI controller 430 encompasses a UI manager 431 and a UI or screen presentation module 432 (presentation module). The presentation module 432 is controlled by the UI manager 431 and may manifest itself, typically, on a visual screen or display 104 on a computing device 102 utilized by the user of the tax return preparation application program 100. The computing device may include the display of a computer, laptop, tablet, mobile phone (e.g., Smartphone), or the like. Different user interface presentations 432 may be invoked depending, for example, on the type of display that is utilized by the computing device. For example, an interview screen with many questions or a significant amount of text may be appropriate for a computer, laptop, or tablet screen but such as presentation may be inappropriate for a mobile computing device such as a mobile phone or Smartphone. In this regard, different interface presentations may be prepared for different types of computing devices. The nature of the interface presentation 432 may not only be tied to a particular computing device but different users may be given different interface presentations 432. For example, a taxpayer that is over the age of 60 may be presented with an interview screen that has larger text or different visual cues than a younger user.
Typically, although not exclusively, in response to a user interface presentation 432 that is generated (e.g., interview screen), a user inputs data to the tax preparation software using an input device such as a mouse, finger tap, keyboard, stylus, voice entry, or the like to respond to questions. The user or taxpayer may also be asked not only to respond to questions but also to include dollar amounts, check or un-check boxes, select one or more options from a pull down menu, select radio buttons, or the like. Free form text entry may also be request of the user or taxpayer. For example, with regard to donated goods, user or taxpayer may be prompted to explain what the donated good are and describe the same in sufficient detail to satisfy requirements set by a particular taxing authority. New or updated data is then reflected in the updated instantiated representation of schema 446 and stored to shared data store 440, and this data may include a user response 436 to a taxpayer data request 417 that was generated and presented to user through an interview screen selected or generated by UI controller 430.
The system 400 also includes a tax calculation engine 480, which reads the current runtime data 442 from shared data store 440, and uses this data as inputs into respective nodes of one or more calculation graphs 482. Respective results or values are calculated with associated functions that are executed with the input data. New or resulting data is written back by tax calculation engine 480 to shared data store 440 for subsequent reading by the TLA 410. For example, if runtime data 442 received thus far includes wages and interest earned from two savings accounts, a function for calculating Adjusted Gross Income (AGI) would sum this wage and interest data, and the resulting AGI value (based on the runtime data received thus far) is written back to shared data store 440. As other types of AGI data are received or imported, tax calculation engine 480 will run calculation graphs 482 again to calculate a new AGI value, which would then be stored to shared data store 440.
TLA 410 outputs tax data that is used to generate the tax return (either electronic return or paper return). The return itself can be prepared by TLA 410 or at the direction of TLA 410 using, for example, a services engine 470 configured to perform a number of tasks or services for the taxpayer. For example, services engine 470 can include a printing option 4701a. Printing option 470a may be used to print a copy of a tax return, tax return data, summaries of tax data, reports, tax forms and schedules, and the like. Services engine 470 may also electronically file 470b or e-file a tax return with a tax authority (e.g., federal or state tax authority or other tax collecting entity). Whether a paper or electronic return is filed, data from shared data store 440 required for particular tax forms, schedules, and the like is transferred over into the desired format. With respect to e-filed tax returns, the tax return may be filed using the MeF web-based system that allows electronic filing of tax returns through the Internet. Of course, other e-filing systems may also be used other than those that rely on the MeF standard. Services engine 470 may also make one or more recommendations 470c based on the run-time data 442 contained in or read by TLA 410. For instance, services engine 470 may identify that a taxpayer has incurred penalties for underpayment of estimates taxes and may recommend to the taxpayer to increase his or her withholdings or estimated tax payments for the following tax year. As another example, services engine 470 may find that a person did not contribute to a retirement plan and may recommend 470c that taxpayer open an Individual Retirement Account (IRA) or look into contributions in an employer-sponsored retirement plan. Services engine 470 may also include a calculator 470d that can be used to calculate various intermediate calculations used as part of the overall tax calculation algorithm. For example, calculator 470d can isolate earned income, investment income, deductions, credits, and the like. Calculator 470d can also be used to estimate tax liability based on certain changed assumptions (e.g., how would my taxes change if I was married and filed a joint return?). Calculator 470d may also be used to compare analyze differences between tax years.
As shown in
After the computer analytic system 900 has generated one or more resource allocation recommendations, the retention module 960 may send the resource allocation recommendations to the TLA 410. In response to the received abandonment indicators, the rule engine 412 in the TLA 410 may utilize a fact cache and generate non-binding suggestions 411 for additional user interface elements to present to a user based on the received resource allocation recommendations. The UI controller 430 may use its UI or user experience manager 431 to determine how to process non-binding suggestions 411.
Having described various aspects of computer analytic systems 900 according to various embodiments, computer-implemented methods for generating resource allocation recommendations using the computer analytic systems 900 will now be described.
At step 504, the computer analytic system 900 stores the received taxpayer data. As described above, the received taxpayer data may be stored as separate, taxpayer specific files, tables, and/or databases.
At step 506, the computer analytic system 900 analyzes the taxpayer data and the indicator to generate a resource allocation recommendation. As described above, the system 900 may analyze the taxpayer data using one or more of a workflow location tracker, a workflow activity history tracker, a taxpayer characteristic identifier, a clustering module, a support vector machine, a decision tree module, a Naïve Bayesian classifier, and/or a neural network.
While certain embodiments have been described with reference to the electronic tax return preparation system 400 and computer analytic system 900 as illustrated in
Additionally, while certain embodiments have been described with reference to taxpayer data as being data within fields of an electronic tax return that is being prepared (i.e., when an electronic tax return is abandoned), embodiments are not so limited. Other embodiments may involve utilizing data from at least one source other than the electronic tax return that includes at least one external input. For example, taxpayer data may be external data such as data of a prior year electronic tax return that was already filed, or other data that has been gathered or collected about the taxpayer, but not yet imported into an electronic tax return. Such data may include data collected from one or more external sources such as a financial management system utilized by the taxpayer (such as MINT or QUICKEN financial management systems), or from one or more other sources 450 shown in
According to one embodiment, external data is utilized as taxpayer data if or when it is available. According to another embodiment, external data is used as taxpayer data only when it has been imported into an electronic tax return and confirmed by the taxpayer.
Further, while certain embodiments have been described with reference to generating resource allocation recommendations by execution of one or more predictive models, embodiments may utilize one or more of these predictive models at different times or simultaneously. For example, during the second iteration of computer analytic system, the system can execute one or more other predictive models compared to the first iteration. Moreover, while certain embodiments have been described with reference to generating resource allocation recommendations for electronic tax return preparation programs, other embodiments may involve generating resource allocation recommendations for any software.
Where methods and steps described above indicate certain events occurring in certain order, those of ordinary skill in the art having the benefit of this disclosure would recognize that the ordering of certain steps may be modified and that such modifications are in accordance with the variations of the disclosed embodiments. Additionally, certain of the steps may be performed concurrently in a parallel process as well as performed sequentially. Thus, the methods shown in various flow diagrams are not intended to be limited to a particular sequential order, unless otherwise stated or required.
Accordingly, embodiments are intended to exemplify alternatives, modifications, and equivalents that may fall within the scope of the claims.
Number | Name | Date | Kind |
---|---|---|---|
4209839 | Bedermen | Jun 1980 | A |
5485544 | Nonaka | Jan 1996 | A |
5500920 | Kupiec | Mar 1996 | A |
5819288 | De Bonet | Oct 1998 | A |
5864482 | Hazama | Jan 1999 | A |
5884283 | Manos | Mar 1999 | A |
5944784 | Simonoff | Aug 1999 | A |
6021397 | Jones et al. | Feb 2000 | A |
6311166 | Nado et al. | Oct 2001 | B1 |
6401080 | Bigus et al. | Jun 2002 | B1 |
6473741 | Baker | Oct 2002 | B1 |
6691116 | Bart | Feb 2004 | B1 |
6718336 | Saffer | Apr 2004 | B1 |
7010507 | Anderson et al. | Mar 2006 | B1 |
7047251 | Reed | May 2006 | B2 |
7149970 | Pratley et al. | Dec 2006 | B1 |
7181438 | Szabo | Feb 2007 | B1 |
7254554 | Tawara et al. | Aug 2007 | B2 |
7289956 | Yu et al. | Oct 2007 | B2 |
7461059 | Richardson et al. | Dec 2008 | B2 |
7539635 | Peak et al. | May 2009 | B1 |
7565312 | Shaw et al. | Jul 2009 | B1 |
7584093 | Potter et al. | Sep 2009 | B2 |
7590572 | Larson | Sep 2009 | B2 |
7603301 | Regan | Oct 2009 | B1 |
7610226 | Miller | Oct 2009 | B1 |
7636742 | Olavarrieta et al. | Dec 2009 | B1 |
7668763 | Albrecht | Feb 2010 | B1 |
7680756 | Quinn | Mar 2010 | B2 |
7685034 | Mori et al. | Mar 2010 | B1 |
7685082 | Coletta et al. | Mar 2010 | B1 |
7693769 | Burlison et al. | Apr 2010 | B1 |
7712023 | Bryan | May 2010 | B1 |
7716094 | Sutter | May 2010 | B1 |
7716099 | Welch et al. | May 2010 | B1 |
7742958 | Leek et al. | Jun 2010 | B1 |
7747484 | Stanley et al. | Jun 2010 | B2 |
7756761 | Albrecht | Jul 2010 | B1 |
7756855 | Ismalon | Jul 2010 | B2 |
7769647 | Char et al. | Aug 2010 | B1 |
7778895 | Baxter et al. | Aug 2010 | B1 |
7788195 | Subrannanian | Aug 2010 | B1 |
7805343 | Lyons et al. | Sep 2010 | B1 |
7818222 | Allanson et al. | Oct 2010 | B2 |
7836406 | Kirsten et al. | Nov 2010 | B1 |
7848971 | Mori et al. | Dec 2010 | B1 |
7853494 | Wyle | Dec 2010 | B2 |
7860763 | Quinn et al. | Dec 2010 | B1 |
7860774 | Peterson et al. | Dec 2010 | B1 |
7870491 | Henderson | Jan 2011 | B1 |
7890442 | Weir et al. | Feb 2011 | B2 |
7904356 | Cobarrubia | Mar 2011 | B1 |
7912767 | Cheatham et al. | Mar 2011 | B1 |
7917411 | Bedell | Mar 2011 | B1 |
7917412 | Wang | Mar 2011 | B1 |
7930226 | Quinn et al. | Apr 2011 | B1 |
7984004 | Andrew et al. | Jul 2011 | B2 |
8001006 | Yu et al. | Aug 2011 | B1 |
8014308 | Gates, III | Sep 2011 | B2 |
8019664 | Tifford et al. | Sep 2011 | B1 |
8024660 | Quinn | Sep 2011 | B1 |
8050988 | Kershner et al. | Nov 2011 | B2 |
8095476 | Bierner et al. | Jan 2012 | B2 |
8099329 | Paulsen | Jan 2012 | B2 |
8108258 | Slattery | Jan 2012 | B1 |
8126716 | Dhanakshirur | Feb 2012 | B2 |
8126787 | Leek et al. | Feb 2012 | B1 |
8190499 | McVickar | May 2012 | B1 |
8204805 | Eftekhari et al. | Jun 2012 | B2 |
8326754 | Bandych | Dec 2012 | B2 |
8346635 | Olim | Jan 2013 | B1 |
8355966 | Vu et al. | Jan 2013 | B1 |
8407113 | Eftekhari et al. | Mar 2013 | B1 |
8417596 | Dunbar et al. | Apr 2013 | B1 |
8417715 | Bruckhaus et al. | Apr 2013 | B1 |
8418920 | Lieberman et al. | Apr 2013 | B2 |
8423444 | MacKrell et al. | Apr 2013 | B1 |
8429184 | Ismon | Apr 2013 | B2 |
8433627 | Agee et al. | Apr 2013 | B2 |
8447667 | Dinamani et al. | May 2013 | B1 |
8452676 | Tan et al. | May 2013 | B1 |
8468110 | Podgorny | Jun 2013 | B1 |
8504582 | Soetarman | Aug 2013 | B2 |
8527375 | Olim | Sep 2013 | B1 |
8583517 | Ohme | Nov 2013 | B1 |
8589262 | Wang | Nov 2013 | B1 |
8606665 | Shaw | Dec 2013 | B1 |
8635127 | Shaw | Jan 2014 | B1 |
8656273 | Tifford et al. | Feb 2014 | B1 |
8689262 | Yamamura | Apr 2014 | B2 |
8694397 | Seubert et al. | Apr 2014 | B2 |
8719120 | McVickar et al. | May 2014 | B1 |
8812380 | Murray et al. | Aug 2014 | B2 |
8857713 | Lieberman et al. | Oct 2014 | B2 |
8874731 | Puppin | Oct 2014 | B1 |
8903810 | Ismon | Dec 2014 | B2 |
8942999 | Fernando et al. | Jan 2015 | B1 |
9037962 | Vassar et al. | May 2015 | B1 |
9069869 | Quinn et al. | Jun 2015 | B1 |
9098586 | Latif | Aug 2015 | B1 |
9117247 | Lieberman et al. | Aug 2015 | B2 |
9153141 | Kane, Jr. | Oct 2015 | B1 |
9201558 | Dingman | Dec 2015 | B1 |
9280252 | Brandmer et al. | Mar 2016 | B1 |
9286282 | Ling, III | Mar 2016 | B2 |
9390402 | Kane, Jr. | Jul 2016 | B1 |
9406089 | Mori et al. | Aug 2016 | B2 |
9412017 | Huang et al. | Aug 2016 | B1 |
9444824 | Bazs et al. | Sep 2016 | B1 |
9690854 | Stent | Jun 2017 | B2 |
9734136 | Mody et al. | Aug 2017 | B1 |
9779129 | Lequeux | Oct 2017 | B1 |
9786017 | Ohme et al. | Oct 2017 | B1 |
9787597 | Miller et al. | Oct 2017 | B1 |
20020002546 | Doerr et al. | Jan 2002 | A1 |
20020015056 | Weinlaender | Feb 2002 | A1 |
20020052774 | Parker et al. | May 2002 | A1 |
20020093529 | Daoud | Jul 2002 | A1 |
20020111888 | Stanley et al. | Aug 2002 | A1 |
20020111890 | Sloan et al. | Aug 2002 | A1 |
20030050876 | Tawara et al. | Mar 2003 | A1 |
20030069882 | Nieswand et al. | Apr 2003 | A1 |
20030115259 | Narayanan | Jun 2003 | A1 |
20040078271 | Morano et al. | Apr 2004 | A1 |
20040254927 | Lang et al. | Dec 2004 | A1 |
20050027632 | Zeitoun et al. | Feb 2005 | A1 |
20050038722 | Throndson et al. | Feb 2005 | A1 |
20050043998 | Bross et al. | Feb 2005 | A1 |
20050054381 | Lee | Mar 2005 | A1 |
20050060174 | Heyward et al. | Mar 2005 | A1 |
20050144072 | Perkowski | Jun 2005 | A1 |
20050160103 | Raffo | Jul 2005 | A1 |
20050210024 | Hursthiller | Sep 2005 | A1 |
20050246234 | Munyon | Nov 2005 | A1 |
20050278221 | Hahn-Carlson et al. | Dec 2005 | A1 |
20050289023 | Hahn-Carlson et al. | Dec 2005 | A1 |
20050289024 | Hahn-Carlson et al. | Dec 2005 | A1 |
20060085304 | Buarque De Macedo et al. | Apr 2006 | A1 |
20060085306 | Schulte et al. | Apr 2006 | A1 |
20060122918 | Graboske et al. | Jun 2006 | A1 |
20060155632 | Cherkas et al. | Jul 2006 | A1 |
20060178961 | Stanley | Aug 2006 | A1 |
20060184410 | Ramamurthy | Aug 2006 | A1 |
20060206454 | Forstl et al. | Sep 2006 | A1 |
20060287890 | Stead | Dec 2006 | A1 |
20070033116 | Murray | Feb 2007 | A1 |
20070055571 | Fox | Mar 2007 | A1 |
20070061128 | Odom | Mar 2007 | A1 |
20070136115 | Senturk et al. | Jun 2007 | A1 |
20070250418 | Banks et al. | Oct 2007 | A1 |
20080027895 | Combaz | Jan 2008 | A1 |
20080027979 | Chandrasekar et al. | Jan 2008 | A1 |
20080059900 | Murray et al. | Mar 2008 | A1 |
20080065617 | Burke et al. | Mar 2008 | A1 |
20080104045 | Cohen | May 2008 | A1 |
20080119134 | Rao | May 2008 | A1 |
20080147494 | Larson | Jun 2008 | A1 |
20080189197 | Ianson et al. | Aug 2008 | A1 |
20080189757 | Schackow et al. | Aug 2008 | A1 |
20080196098 | Cottrell | Aug 2008 | A1 |
20080201206 | Pokorney | Aug 2008 | A1 |
20080263643 | Jaiswal | Oct 2008 | A1 |
20080288304 | Nores | Nov 2008 | A1 |
20090012884 | Harman et al. | Jan 2009 | A1 |
20090031042 | Phatak | Jan 2009 | A1 |
20090076335 | Schwarzberg et al. | Mar 2009 | A1 |
20090099959 | Liao | Apr 2009 | A1 |
20090234684 | Stoke et al. | Sep 2009 | A1 |
20090276374 | Viner | Nov 2009 | A1 |
20090307159 | Pinckney et al. | Dec 2009 | A1 |
20100010849 | Hurd | Jan 2010 | A1 |
20100017348 | Pinckney et al. | Jan 2010 | A1 |
20100023934 | Sheehan et al. | Jan 2010 | A1 |
20100146523 | Brigaut et al. | Jun 2010 | A1 |
20100251305 | Kimble et al. | Sep 2010 | A1 |
20100262495 | Dumon et al. | Oct 2010 | A1 |
20100274606 | Fain et al. | Oct 2010 | A1 |
20100312724 | Pinckney et al. | Dec 2010 | A1 |
20100332362 | Ramsey et al. | Dec 2010 | A1 |
20110004537 | Ianson et al. | Jan 2011 | A1 |
20110022502 | Evans | Jan 2011 | A1 |
20110066602 | Studer | Mar 2011 | A1 |
20110078066 | Sherman et al. | Mar 2011 | A1 |
20110119264 | Hu et al. | May 2011 | A1 |
20110137776 | Goad et al. | Jun 2011 | A1 |
20110173222 | Sayal | Jul 2011 | A1 |
20110258195 | Welling et al. | Oct 2011 | A1 |
20110264569 | Houseworth et al. | Oct 2011 | A1 |
20110264570 | Houseworth | Oct 2011 | A1 |
20120030159 | Pilaszy et al. | Feb 2012 | A1 |
20120030767 | Rippert, Jr. | Feb 2012 | A1 |
20120053965 | Hellman et al. | Mar 2012 | A1 |
20120084185 | Ciaramitaro et al. | Apr 2012 | A1 |
20120109792 | Eftekhari et al. | May 2012 | A1 |
20120136764 | Miller et al. | May 2012 | A1 |
20120211561 | Lieberman et al. | Aug 2012 | A1 |
20120215669 | Lieberman et al. | Aug 2012 | A1 |
20120278179 | Ray et al. | Nov 2012 | A1 |
20120303495 | Murray | Nov 2012 | A1 |
20120324393 | Mbenkum | Dec 2012 | A1 |
20130080302 | Ianson et al. | Mar 2013 | A1 |
20130091050 | Merrill | Apr 2013 | A1 |
20130124644 | Hunt et al. | May 2013 | A1 |
20130198047 | Houseworth et al. | Aug 2013 | A1 |
20130198287 | Raz | Aug 2013 | A1 |
20130254151 | Mohagheghi et al. | Sep 2013 | A1 |
20130282539 | Murray | Oct 2013 | A1 |
20130282733 | Tawakol | Oct 2013 | A1 |
20130290200 | Singh | Oct 2013 | A1 |
20140027509 | Lieberman et al. | Jan 2014 | A1 |
20140032259 | LaFever | Jan 2014 | A1 |
20140068413 | Christensen | Mar 2014 | A1 |
20140101571 | Lewis | Apr 2014 | A1 |
20140114822 | Sharma | Apr 2014 | A1 |
20140156566 | Kabiljo et al. | Jun 2014 | A1 |
20140172656 | Shaw | Jun 2014 | A1 |
20140180883 | Regan | Jun 2014 | A1 |
20140201045 | Pai et al. | Jul 2014 | A1 |
20140201108 | Chapman | Jul 2014 | A1 |
20140214636 | Rajsky | Jul 2014 | A1 |
20140222702 | Jennings | Aug 2014 | A1 |
20140244455 | Huang et al. | Aug 2014 | A1 |
20140244456 | Huang et al. | Aug 2014 | A1 |
20140248063 | Chourasia | Sep 2014 | A1 |
20140279190 | Severinghaus et al. | Sep 2014 | A1 |
20140314225 | Riahi et al. | Oct 2014 | A1 |
20140324648 | Mori et al. | Oct 2014 | A1 |
20140325664 | Nekhoroshev | Oct 2014 | A1 |
20140337189 | Barsade et al. | Nov 2014 | A1 |
20140337753 | McKellar et al. | Nov 2014 | A1 |
20150007065 | Krishnamoorthy | Jan 2015 | A1 |
20150026146 | Mance | Jan 2015 | A1 |
20150081470 | Westphal | Mar 2015 | A1 |
20150101599 | Berry | Apr 2015 | A1 |
20150149877 | Ling, III | May 2015 | A1 |
20150178371 | Seth | Jun 2015 | A1 |
20150332167 | Kaush et al. | Nov 2015 | A1 |
20150363875 | Guerry | Dec 2015 | A1 |
20150379631 | Singh | Dec 2015 | A1 |
20160034853 | Wang | Feb 2016 | A1 |
20160180248 | Regan | Feb 2016 | A1 |
20160071112 | Unser | Mar 2016 | A1 |
20160078567 | Goldman et al. | Mar 2016 | A1 |
20160098804 | Mascaro et al. | Apr 2016 | A1 |
20160125552 | Pathak et al. | May 2016 | A1 |
20160148322 | Mascaro et al. | May 2016 | A1 |
20160180470 | Mascaro et al. | Jun 2016 | A1 |
20160217533 | Laaser | Jul 2016 | A1 |
20160217534 | Goldman et al. | Jul 2016 | A1 |
20160246762 | Eaton | Aug 2016 | A1 |
20160247239 | Houseworth et al. | Aug 2016 | A1 |
20160275627 | Wang et al. | Sep 2016 | A1 |
20160328804 | Mori et al. | Nov 2016 | A1 |
20160328805 | Mori et al. | Nov 2016 | A1 |
20160328806 | Mori et al. | Nov 2016 | A1 |
20170004585 | Dang et al. | Jan 2017 | A1 |
20170104841 | Duke | Apr 2017 | A1 |
20170132314 | Liu et al. | May 2017 | A1 |
Number | Date | Country |
---|---|---|
2002-099613 | Apr 2002 | JP |
10-2009-0089225 | Aug 2009 | KR |
10-2013-0027811 | Mar 2013 | KR |
WO 2004008367 | Jan 2004 | WO |
Entry |
---|
U.S. Appl. No. 15/363,681, filed Nov. 29, 2016 (Nov. 6, 2020 to Feb. 6, 2020). |
U.S. Appl. No. 14/871,366, filed Sep. 30, 2015 (Nov. 6, 2020 to Feb. 6, 2020). |
U.S. Appl. No. 14/925,633, filed Oct. 28, 2015 (Nov. 6, 2020 to Feb. 6, 2020). |
U.S. Appl. No. 15/363,681, filed Nov. 29, 2016. |
U.S. Appl. No. 14/530,305, filed Oct. 31, 2014. |
U.S. Appl. No. 14/530,369, filed Oct. 31, 2014. |
U.S. Appl. No. 14/607,935, filed Jan. 28, 2015. |
U.S. Appl. No. 12/475,767, filed Jun. 1, 2009. |
U.S. Appl. No. 11/413,308, filed Apr. 28, 2006. |
U.S. Appl. No. 14/674,582, filed Mar. 31, 2015. |
U.S. Appl. No. 15/164,777, filed May 25, 2016. |
U.S. Appl. No. 14/871,366, filed Sep. 30, 2015. |
U.S. Appl. No. 14/925,633, filed Oct. 28, 2015. |
U.S. Appl. No. 16/295,417, filed Mar. 7, 2019. |
U.S. Appl. No. 16/524,825, filed Jul. 29, 2019. |
U.S. Appl. No. 14/484,119, filed Sep. 11, 2014. |
English Language Abstract of KR 10-2013-0027811 published Mar. 18, 2013. |
English Language Abstract of KR 10-2009-0089225 published Aug. 21, 2009. |
English Language Abstract of JP 2002-099613 published Apr. 5, 2002. |
web.archive.org/web/20100919125845/http://cpaclass.conn/tax-accounting/tax-law/internal-revenue-code/26-usc-section/196.htnn, CPA, class, U.S. Tax Laws Internal Revenue Code, Sep. 19, 2010 (Year: 2010). |
“Modular Programming,” Wikipedia, the free encyclopedia, Jul. 29, 2014, http://en.wikipedia.org/w/index.php?title=Modular_programming&oldid=618953117, retrieved from the Internet on Mar. 31, 2015, 4 pages. |
Anders, B. Susan; “Website of the Month: MSN Money Tax Center,” Apr. 2013, The CPA Journal, pp. 72-73. |
Forsati, R.; “Web Page Personalization Based on Weighted Association Rules,” 2009 International Conference on Electronic Computer Technology, pp. 130-135. |
http://en.wikipedia.org/wiki/Artificial_neural_network, printed Oct. 27, 2014 (22 pages). |
http://en.wikipedia.org/wiki/Declarative_programming, printed Oct. 27, 2014 (4 pages). |
http://en.wikipedia.org/wiki/Generalized_linear_model, printed Oct. 27, 2014 (13 pages). |
http://en.wikipedia.org/wiki/Gradient_boosting, printed Oct. 27, 2014 (8 pages). |
http://en.wikipedia.org/wiki/Imperative_programming, printed Oct. 27, 2014 (4 pages). |
http://en.wikipedia.org/wiki/K-d_tree, printed Oct. 27, 2014 (10 pages). |
http://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm, printed Oct. 27, 2014 (10 pages). |
http://en.wikipedia.org/wiki/Logistic_regression, printed Oct. 27, 2014 (28 pages). |
http://en.wikipedia.org/wiki/Naive_Bayes_classifier, printed Oct. 27, 2014 (14 pages). |
http://en.wikipedia.org/wiki/Predictive_analytics, printed Oct. 27, 2014 (18 pages). |
http://en.wikipedia.org/wiki/Predictive_modelling, printed Oct. 27, 2014 (8 pages). |
http://en.wikipedia.org/wiki/Random_forest, printed Oct. 27, 2014 (7 pages). |
http://en.wikipedia.org/wiki/Support_vector_machine, printed Oct. 27, 2014 (16 pages). |
http://www.forbes.com/sites/danwoods/2013/04/171why-adopting-the-declarative-programming-practices-will-improve-your-return-from-technology/, printed Oct. 27, 2014 (8 pages). |
http://www.gartner.com/it-glossary/predictive-modeling, printed Oct. 27, 2014 (1 page). |
http://www.ibm.com/developerworks/library/ba-predictive-analytics2/, printed Oct. 27, 2014 (8 pages). |
PCT International Search Report for PCT/US2014/056516 dated Jun. 18, 2015 (3 pages). |
PCT Written Opinion of the International Search Authority for PCT/US2014/056516 dated Jun. 18, 2015 (9 pages). |
Publication 559: Final Income Tax Return for Decedent—Form 1040, p. 2, paragraph 2; https://taxmap.ntis.gov/taxmap/pub/p559-001.htm; retrieved from the Internet Jul. 11, 2017. |
Zhang, Zhenya, et al.; “Enabling Personalization Recommendation with Weighted FP for Text Information Retrieval Based on User-Focus,” Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC'04), (5 pages). |
“QuickBooks® Assessing the Health of the Data File and Troubleshooting”, The Sleeter Group, Aug. 2005 (71 pages). |
U.S. Appl. No. 14/698,645, filed Apr. 28, 2015. |
U.S. Appl. No. 15/363,681, filed Nov. 29, 2016 (Feb. 6, 2020 to present). |
U.S. Appl. No. 14/925,633, filed Oct. 28, 2015 (Feb. 6, 2020 to present). |
U.S. Appl. No. 14/484,119, filed Sep. 11, 2014 (Mar. 15, 2020 to present). |